• Smart Media Journal
• /
• v.10 no.1
• /
• pp.39-46
• /
• 2021

This study is about a method of extracting a summary from a news article in consideration of the importance of each sentence constituting the article. We propose a method of calculating sentence importance by extracting the probabilities of topic sentence, similarity with article title and other sentences, and sentence position as characteristics that affect sentence importance. At this time, a hypothesis is established that the Topic Sentence will have a characteristic distinct from the general sentence, and a deep learning-based classification model is trained to obtain a topic sentence probability value for the input sentence. Also, using the pre-learned ELMo language model, the similarity between sentences is calculated based on the sentence vector value reflecting the context information and extracted as sentence characteristics. The topic sentence classification performance of the LSTM and BERT models was 93% accurate, 96.22% recall, and 89.5% precision, resulting in high analysis results. As a result of calculating the importance of each sentence by combining the extracted sentence characteristics, it was confirmed that the performance of extracting the topic sentence was improved by about 10% compared to the existing TextRank algorithm.

• Journal of Information Processing Systems
• /
• v.16 no.4
• /
• pp.820-831
• /
• 2020

Extractive document summarization aims to select a few sentences while preserving its main information on a given document, but the current extractive methods do not consider the sentence-information repeat problem especially for news document summarization. In view of the importance and redundancy of news text information, in this paper, we propose a neural extractive summarization approach with joint sentence semantic clipping and selection, which can effectively solve the problem of news text summary sentence repetition. Specifically, a hierarchical selective encoding network is constructed for both sentence-level and document-level document representations, and data containing important information is extracted on news text; a sentence extractor strategy is then adopted for joint scoring and redundant information clipping. This way, our model strikes a balance between important information extraction and redundant information filtering. Experimental results on both CNN/Daily Mail dataset and Court Public Opinion News dataset we built are presented to show the effectiveness of our proposed approach in terms of ROUGE metrics, especially for redundant information filtering.

• Journal of Information Processing Systems
• /
• v.13 no.4
• /
• pp.752-777
• /
• 2017

This paper proposes an automatic method to summarize Bangla news document. In the proposed approach, pronoun replacement is accomplished for the first time to minimize the dangling pronoun from summary. After replacing pronoun, sentences are ranked using term frequency, sentence frequency, numerical figures and title words. If two sentences have at least 60% cosine similarity, the frequency of the larger sentence is increased, and the smaller sentence is removed to eliminate redundancy. Moreover, the first sentence is included in summary always if it contains any title word. In Bangla text, numerical figures can be presented both in words and digits with a variety of forms. All these forms are identified to assess the importance of sentences. We have used the rule-based system in this approach with hidden Markov model and Markov chain model. To explore the rules, we have analyzed 3,000 Bangla news documents and studied some Bangla grammar books. A series of experiments are performed on 200 Bangla news documents and 600 summaries (3 summaries are for each document). The evaluation results demonstrate the effectiveness of the proposed technique over the four latest methods.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.3
• /
• pp.125-132
• /
• 2022

Sentence compression is a natural language processing task that generates concise sentences that preserves the important meaning of the original sentence. For grammatically appropriate sentence compression, early studies utilized human-defined linguistic rules. Furthermore, while the sequence-to-sequence models perform well on various natural language processing tasks, such as machine translation, there have been studies that utilize it for sentence compression. However, for the linguistic rule-based studies, all rules have to be defined by human, and for the sequence-to-sequence model based studies require a large amount of parallel data for model training. In order to address these challenges, Deleter, a sentence compression model that leverages a pre-trained language model BERT, is proposed. Because the Deleter utilizes perplexity based score computed over BERT to compress sentences, any linguistic rules and parallel dataset is not required for sentence compression. However, because Deleter compresses sentences only considering perplexity, it does not compress sentences by reflecting the linguistic information of the words in the sentences. Furthermore, since the dataset used for pre-learning BERT are far from compressed sentences, there is a problem that this can lad to incorrect sentence compression. In order to address these problems, this paper proposes a method to quantify the importance of linguistic information and reflect it in perplexity-based sentence scoring. Furthermore, by fine-tuning BERT with a corpus of news articles that often contain proper nouns and often omit the unnecessary modifiers, we allow BERT to measure the perplexity appropriate for sentence compression. The evaluations on the English and Korean dataset confirm that the sentence compression performance of sentence-scoring based models can be improved by utilizing the proposed method.

• Smart Media Journal
• /
• v.11 no.3
• /
• pp.31-38
• /
• 2022

In the document extraction summary study, various methods for selecting important sentences based on the relationship between sentences were proposed. In the Korean document summary using the summation similarity of sentences, the summation similarity of the sentences was regarded as the amount of sentence information, and the summary sentences were extracted by selecting important sentences based on this. However, the problem is that it does not take into account the various importance that each sentence contributes to the entire document. Therefore, in this study, we propose a document extraction summary method that provides a summary by selecting important sentences based on the amount of quantitative and semantic information in the sentence. As a result, the extracted sentence agreement was 58.56% and the ROUGE-L score was 34, which was superior to the method using only the combined similarity. Compared to the deep learning-based method, the extraction method is lighter, but the performance is similar. Through this, it was confirmed that the method of compressing information based on semantic similarity between sentences is an important approach in document extraction summary. In addition, based on the quickly extracted summary, the document generation summary step can be effectively performed.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.32B no.1
• /
• pp.136-146
• /
• 1995

In this paper, a Japanese morphological analyzer for Japanese to Korean Machine Translation System is designed. The analyzer reconstructs the Japanese input sentence into word phrases that include grammatical and dictionary informations. Thus we propose the algorithm to separate morphemes and then connect them by reference to a corresponding Korean word phrases. And we define the connector to control Japanese word phrases It is used in controlling the start and the end point of the word phrase in the Japanese sentence which is without a space. The proposed analyzer uses the analysis dictionary to perform more efficient analysis than the existing analyzer. And we can decrease the number of its dictionary searches. Since the analyzer, proposed in this paper, for Japanese to Korean Machine Translation System processes each word phrase in consideration of the corresponding Korean word phrase, it can generate more accurate Korean expressions than the existing one which places great importance on the generation of the entire sentence structure.

• Speech Sciences
• /
• v.11 no.2
• /
• pp.105-117
• /
• 2004

Recently, many scholars have emphasized the importance of English listening ability for smoother communication. Most audio materials, however, were recorded in a quiet sound-proof booth. Therefore, students who have spent so much time listening to the ideal audio materials are expected to have difficulty communicating with native speakers in the real life. In this study, we examined how well thirty three Korean university students and five native speakers will repeat the recorded English sentences under noise and speed conditions. The subjects' production was scored by listening to each recorded sentence and counting the number of words correctly produced and determined the percent ratios of correctly produced words to the total words in each sentence. Results showed that the student group correctly repeated around 65% of all the words in each sentence while the native speakers demonstrated almost perfect match. It seemed that the students had difficulty perceiving and repeating function words in various conditions. Also, high-proficiency student group outperformed the low-proficiency student group particularly in their repetition of function words. In addition, the student subjects' accuracy of repetition remarkably dropped when the normal sentences were both sped up and mixed with noise. Finally, it was observed that the Korean students' percent correct ratio fell down as the stimulus sentence became longer.

• Journal of KIISE:Software and Applications
• /
• v.32 no.5
• /
• pp.396-405
• /
• 2005

Since sentences are the basic propositional units of text, their themes would be helpful for various tasks that require knowledge about the semantic content of text. Despite the importance of determining the theme of a sentence, however, few studies have investigated the problem of automatically assigning the theme to a sentence. Therefore, we propose a sentence theme allocation scheme based on the head-driven patterns of sentences in encyclopedia. In a serious of experiments using Dusan Dong-A encyclopedia, the proposed method outperformed the baseline of the theme allocation performance. The head-driven pattern 4, which is reconfigured based on the predicate, showed superior performance in the theme allocation with the average F-score of $98.96\%$ for the training data, and $88.57\%$ for the test data.

• Journal of KIISE:Software and Applications
• /
• v.29 no.6
• /
• pp.417-424
• /
• 2002

Automatic text categorization is a problem of assigning predefined categories to free text documents. In order to classify text documents, we have to extract good features from them. In previous researches, a text document is commonly represented by the frequency of each feature. But there is a difference between important and unimportant sentences in a text document. It has an effect on the importance of features in a text document. In this paper, we measure the importance of sentences in a text document using text summarizing techniques. A text document is represented by features with different weights according to the importance of each sentence. To verify the new method, we constructed Korean news group data set and experiment our method using it. We found that our new method gale a significant improvement over a basis system for our data sets.

• Journal of The Korean Association For Science Education
• /
• v.44 no.3
• /
• pp.231-248
• /
• 2024

This study developed a chatbot for first-year high school students, employing open-source software and the Korean Sentence-BERT model for AI-powered document classification. The chatbot utilizes the Sentence-BERT model to find the six most similar Q&A pairs to a student's query and presents them in a carousel format. The initial dataset, built from online resources, was refined and expanded based on student feedback and usability throughout over the operational period. By the end of the 2023 academic year, the chatbot integrated a total of 30,819 datasets and recorded 3,457 student interactions. Analysis revealed students' inclination to use the chatbot when prompted by teachers during classes and primarily during self-study sessions after school, with an average of 2.1 to 2.2 inquiries per session, mostly via mobile phones. Text mining identified student input terms encompassing not only science-related queries but also aspects of school life such as assessment scope. Topic modeling using BERTopic, based on Sentence-BERT, categorized 88% of student questions into 35 topics, shedding light on common student interests. A year-end survey confirmed the efficacy of the carousel format and the chatbot's role in addressing curiosities beyond integrated science learning objectives. This study underscores the importance of developing chatbots tailored for student use in public education and highlights their educational potential through long-term usage analysis.